Towards Context-Aware Domain Generalization: Understanding the Benefits and Limits of Marginal Transfer Learning

• URL: http://arxiv.org/abs/2312.10107v2
• Date: Wed, 21 Feb 2024 13:57:19 GMT
• Title: Towards Context-Aware Domain Generalization: Understanding the Benefits and Limits of Marginal Transfer Learning
• Authors: Jens M\"uller, Lars K\"uhmichel, Martin Rohbeck, Stefan T. Radev, Ullrich K\"othe
• Abstract summary: We formalize the notion of context as a permutation-invariant representation of a set of data points. Empirical analysis shows that our criteria are effective in discerning both favorable and unfavorable scenarios.
• Score: 1.5320861212113897
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In this work, we analyze the conditions under which information about the context of an input $X$ can improve the predictions of deep learning models in new domains. Following work in marginal transfer learning in Domain Generalization (DG), we formalize the notion of context as a permutation-invariant representation of a set of data points that originate from the same domain as the input itself. We offer a theoretical analysis of the conditions under which this approach can, in principle, yield benefits, and formulate two necessary criteria that can be easily verified in practice. Additionally, we contribute insights into the kind of distribution shifts for which the marginal transfer learning approach promises robustness. Empirical analysis shows that our criteria are effective in discerning both favorable and unfavorable scenarios. Finally, we demonstrate that we can reliably detect scenarios where a model is tasked with unwarranted extrapolation in out-of-distribution (OOD) domains, identifying potential failure cases. Consequently, we showcase a method to select between the most predictive and the most robust model, circumventing the well-known trade-off between predictive performance and robustness.

Related papers

• Harnessing the Power of Vicinity-Informed Analysis for Classification under Covariate Shift [9.530897053573186]
  Transfer learning enhances prediction accuracy on a target distribution by leveraging data from a source distribution. This paper introduces a novel dissimilarity measure that utilizes vicinity information, i.e., the local structure of data points. We characterize the excess error using the proposed measure and demonstrate faster or competitive convergence rates compared to previous techniques.
  arXiv  Detail & Related papers  (2024-05-27T07:55:27Z)
• Optimal Aggregation of Prediction Intervals under Unsupervised Domain Shift [9.387706860375461]
  A distribution shift occurs when the underlying data-generating process changes, leading to a deviation in the model's performance. The prediction interval serves as a crucial tool for characterizing uncertainties induced by their underlying distribution. We propose methodologies for aggregating prediction intervals to obtain one with minimal width and adequate coverage on the target domain.
  arXiv  Detail & Related papers  (2024-05-16T17:55:42Z)
• Modeling Uncertain Feature Representation for Domain Generalization [49.129544670700525]
  We show that our method consistently improves the network generalization ability on multiple vision tasks. Our methods are simple yet effective and can be readily integrated into networks without additional trainable parameters or loss constraints.
  arXiv  Detail & Related papers  (2023-01-16T14:25:02Z)
• Domain-Adjusted Regression or: ERM May Already Learn Features Sufficient for Out-of-Distribution Generalization [52.7137956951533]
  We argue that devising simpler methods for learning predictors on existing features is a promising direction for future research. We introduce Domain-Adjusted Regression (DARE), a convex objective for learning a linear predictor that is provably robust under a new model of distribution shift. Under a natural model, we prove that the DARE solution is the minimax-optimal predictor for a constrained set of test distributions.
  arXiv  Detail & Related papers  (2022-02-14T16:42:16Z)
• Regularizing Variational Autoencoder with Diversity and Uncertainty Awareness [61.827054365139645]
  Variational Autoencoder (VAE) approximates the posterior of latent variables based on amortized variational inference. We propose an alternative model, DU-VAE, for learning a more Diverse and less Uncertain latent space.
  arXiv  Detail & Related papers  (2021-10-24T07:58:13Z)
• Fair Representation Learning using Interpolation Enabled Disentanglement [9.043741281011304]
  We propose a novel method to address two key issues: (a) Can we simultaneously learn fair disentangled representations while ensuring the utility of the learned representation for downstream tasks, and (b)Can we provide theoretical insights into when the proposed approach will be both fair and accurate. To address the former, we propose the method FRIED, Fair Representation learning using Interpolation Enabled Disentanglement.
  arXiv  Detail & Related papers  (2021-07-31T17:32:12Z)
• On the benefits of representation regularization in invariance based domain generalization [6.197602794925773]
  Domain generalization aims to alleviate such a prediction gap between the observed and unseen environments. In this paper, we reveal that merely learning invariant representation is vulnerable to the unseen environment. Our analysis further inspires an efficient regularization method to improve the robustness in domain generalization.
  arXiv  Detail & Related papers  (2021-05-30T13:13:55Z)
• A Bit More Bayesian: Domain-Invariant Learning with Uncertainty [111.22588110362705]
  Domain generalization is challenging due to the domain shift and the uncertainty caused by the inaccessibility of target domain data. In this paper, we address both challenges with a probabilistic framework based on variational Bayesian inference. We derive domain-invariant representations and classifiers, which are jointly established in a two-layer Bayesian neural network.
  arXiv  Detail & Related papers  (2021-05-09T21:33:27Z)
• Learning Invariant Representations and Risks for Semi-supervised Domain Adaptation [109.73983088432364]
  We propose the first method that aims to simultaneously learn invariant representations and risks under the setting of semi-supervised domain adaptation (Semi-DA) We introduce the LIRR algorithm for jointly textbfLearning textbfInvariant textbfRepresentations and textbfRisks.
  arXiv  Detail & Related papers  (2020-10-09T15:42:35Z)
• Learning to Learn with Variational Information Bottleneck for Domain Generalization [128.90691697063616]
  Domain generalization models learn to generalize to previously unseen domains, but suffer from prediction uncertainty and domain shift. We introduce a probabilistic meta-learning model for domain generalization, in which parameters shared across domains are modeled as distributions. To deal with domain shift, we learn domain-invariant representations by the proposed principle of meta variational information bottleneck, we call MetaVIB.
  arXiv  Detail & Related papers  (2020-07-15T12:05:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.